Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 998 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.5906. Min Act: -0.1700

Data Index: 1310295 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.5906. Min Act: -0.1700

Data Index: 648086 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.4967. Min Act: -0.1700

Data Index: 20773 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.4653. Min Act: -0.1700

Data Index: 859917 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.4496. Min Act: -0.1700

Data Index: 886985 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.4496. Min Act: -0.1700

Data Index: 210018 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1232267 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.4340. Min Act: -0.1700

Data Index: 701597 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3712. Min Act: -0.1700

Data Index: 1022761 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3869. Min Act: -0.1700

Data Index: 1206729 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3712. Min Act: -0.1700

Data Index: 806833 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3712. Min Act: -0.1700

Data Index: 212920 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3869. Min Act: -0.1700

Data Index: 249807 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3712. Min Act: -0.1700

Data Index: 118480 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3869. Min Act: -0.1700

Data Index: 235073 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3084. Min Act: -0.1700

Data Index: 221090 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3869. Min Act: -0.1700

Data Index: 946343 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3555. Min Act: -0.1700

Data Index: 13490 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3398. Min Act: -0.1700

Data Index: 658798 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 3.5906. Min Range: -3.5906

Max Act: 3.3555. Min Act: -0.1700

Data Index: 888708 (C4 (Web Text))

Max Activating Token Index: 231